James Bowes - Post 16 Computer Science

GPUs are good at processing multiple jobs in parallel at the same time. GPUs are graphics processing units which are traditionally responsible for the processing of large blocks of visual data, very quickly. They are co-processors so work alongside the CPU to complete the task.

Taken from Quora  - "CPU Pipelining in simple terms": A pipeline is a way of making computers run faster. It does so by taking several steps that a computer (CPU) needs to do the execute a single instruction and overlaps them, so the computer is running those steps in parallel, The number of stages in the pipeline impact how many steps the computer can do in parallel. When you do the steps in parallel, you make each step shorter and simpler, which means you can to run the clock faster, and thus run the computer faster.

1)  The first instruction is passed to the program counter.  2) The address of the data required to carry out this instruction is sent to the memory address register.  3) The address is then sent via the address bus to the RAM where the data is collected and sent back to the memory data register via the data bus. 4) The data is then decoded when passing through the current instruction register where it is decided what needs to be done.  5) The data is then processed within the Accumulator.  6) The data is then transferred to the memory data register and then the memory address register before it is transferred by the address/data bus back to the RAM for storage.